检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Liu, Junping Yang, Shichen Peng, Tao Hu, Xinrong Zhu, Qiang Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion China Engineering Research Center of Hubei Province for Clothing Information China Wuhan Textile University School of Computer Science and Artificial Intelligence China

ISBN: (纸本)9798350337488

Automated International Classification of Diseases (icd) coding involves the automated assignment of diverse disease codes to clinical medical texts. It is considered as a multi-label classification task. Because most icd codes are rare, the imbalanced distribution and small sample size issue make this task challenging. Inspired by the recent success of ChatGPT and prompt-based fine-tuning, this study proposes a model called Chaticd to address the issue of few-shot icd coding. First, ChatGPT for data augumentation rephrases the descriptions of icd codes into multiple samples. Then, Chaticd fine-tunes the pretrained model by generating prompt templates and label mapping words. We conduct an evaluation of Chaticd on benchmark datasets, namely MIMIC-III-50 and MIMIC-III-rare50. On the few-shot icd coding task of MIMIC-III-rare50, Chaticd achieves macro-F1 and micro-F1 of 35.8% and 38.2% respectively, which is a 5.4% and 5.6% improvement over the current best model. © 2023 IEEE.

关键词： ChatGPT Few-shot Learning icd coding Prompt-based Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Automated icd coding using extreme multi-label long text transformer-based models

引用

ARTIFICIAL INTELLIGENCE IN MEDICINE 2023年第1期144卷 102662-102662页

作者： Liu, Leibo Perez-Concha, Oscar Nguyen, Anthony Bennett, Vicki Jorm, Louisa Univ New South Wales Ctr Big Data Res Hlth Sydney Australia CSIRO Australian eHlth Res Ctr Brisbane Qld Australia Australian Inst Hlth & Welf Informat Management & Classificat Unit MIMCU Metadata Canberra ACT Australia Univ New South Wales Sydney Ctr Big Data Res Hlth Level 2AGSM Bldg G27 Kensington NSW 2052 Australia

Encouraged by the success of pretrained Transformer models in many natural language processing tasks, their use for International Classification of Diseases (icd) coding tasks is now actively being explored. In this study, we investigated two existing Transformer-based models (PLM-icd and XR-Transformer) and proposed a novel Transformer-based model (XR-LAT), aiming to address the extreme label set and long text classification challenges that are posed by automated icd coding tasks. The Transformer-based model PLM-icd, which currently holds the state-of-the-art (SOTA) performance on the icd coding benchmark datasets MIMIC-III and MIMIC-II, was selected as our baseline model for further optimisation on both datasets. In addition, we extended the capabilities of the leading model in the general extreme multi-label text classification domain, XR-Transformer, to support longer sequences and trained it on both datasets. Moreover, we proposed a novel model, XR-LAT, which was also trained on both datasets. XR-LAT is a recursively trained model chain on a predefined hierarchical code tree with label-wise attention, knowledge transferring and dynamic negative sampling mechanisms. Our optimised PLM-icd models, which were trained with longer total and chunk sequence lengths, significantly outperformed the current SOTA PLM-icd models, and achieved the highest micro-F1 scores of 60.8 % and 50.9 % on MIMIC-III and MIMIC-II, respectively. The XR-Transformer model, although SOTA in the general domain, did not perform well across all metrics. The best XR-LAT based models obtained results that were competitive with the current SOTA PLM-icd models, including improving the macro-AUC by 2.1 % and 5.1 % on MIMIC-III and MIMIC-II, respectively. Our optimised PLM-icd models are the new SOTA models for automated icd coding on both datasets, while our novel XR-LAT models perform competitively with the previous SOTA PLM-icd models.

关键词： Transformers icd coding Extreme multi-label long text classification MIMIC-III MIMIC-II Discharge summaries

来源：评论

学校读者我要写书评

暂无评论

Hierarchical label-wise attention transformer model for explainable icd coding

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2022年第0期133卷 104161页

作者： Liu, Leibo Perez-Concha, Oscar Nguyen, Anthony Bennett, Vicki Jorm, Louisa Univ New South Wales Ctr Big Data Res Hlth Sydney NSW Australia CSIRO Australian E Hlth Res Ctr Brisbane Qld Australia Australian Inst Hlth & Welf Metadata Informat Management & Classificat Unit M Canberra ACT Australia

International Classification of Diseases (icd) coding plays an important role in systematically classifying morbidity and mortality data. In this study, we propose a hierarchical label-wise attention Transformer model (HiLAT) for the explainable prediction of icd codes from clinical documents. HiLAT firstly fine-tunes a pretrained Transformer model to represent the tokens of clinical documents. We subsequently employ a two-level hierarchical label-wise attention mechanism that creates label-specific document representations. These representations are in turn used by a feed-forward neural network to predict whether a specific icd code is assigned to the input clinical document of interest. We evaluate HiLAT using hospital discharge summaries and their corresponding icd-9 codes from the MIMIC-III database. To investigate the performance of different types of Transformer models, we develop ClinicalplusXLNet, which conducts continual pretraining from XLNet-Base using all the MIMIC-III clinical notes. The experiment results show that the F1 scores of the HiLAT + ClinicalplusXLNet outperform the previous state-of-the-art models for the top-50 most frequent icd-9 codes from MIMIC-III. Visualisations of attention weights present a potential explainability tool for checking the face validity of icd code predictions.

关键词： Hierarchical label-wise attention Transformers Explainability icd coding MIMIC-III

来源：评论

学校读者我要写书评

暂无评论

Retrieve and rerank for automated icd coding via Contrastive Learning

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2023年第1期143卷 104396页

作者： Niu, Kunying Wu, Yifan Li, Yaohang Li, Min Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Old Dominion Univ Dept Comp Sci Norfolk VA USA

Automated icd coding is a multi-label prediction task aiming at assigning patient diagnoses with the most relevant subsets of disease codes. In the deep learning regime, recent works have suffered from large label set and heavy imbalance distribution. To mitigate the negative effect in such scenarios, we propose a retrieve and rerank framework that introduces the Contrastive Learning (CL) for label retrieval, allowing the model to make more accurate prediction from a simplified label space. Given the appealing discriminative power of CL, we adopt it as the training strategy to replace the standard cross-entropy objective and retrieve a small subset by taking the distance between clinical notes and icd codes into account. After properly training, the retriever could implicitly capture the code co-occurrence, which makes up for the deficiency of cross-entropy assigning each label independently of the others. Further, we evolve a powerful model via a Transformer variant for refining and reranking the candidate set, which can extract semantically meaningful features from long clinical sequences. Applying our method on well-known models, experiments show that our framework provides more accurate results guaranteed by preselecting a small subset of candidates before fine-level reranking. Relying on the framework, our proposed model achieves 0.590 and 0.990 in terms of Micro-F1 and Micro-AUC on benchmark MIMIC-III.

关键词： icd coding Retrieve Rerank Contrastive learning Multi-label classification

来源：评论

学校读者我要写书评

暂无评论

icdXML: enhancing icd coding with probabilistic label trees and dynamic semantic representations

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-12页

作者： Wang, Zeqiang Wang, Yuqi Zhang, Haiyang Wang, Wei Qi, Jun Chen, Jianjun Sastry, Nishanth Johnson, Jon De, Suparna Xian Jiaotong Liverpool Univ Dept Comp Suzhou 21500 Peoples R China Univ Surrey Sch Comp Sci & Elect Engn Guildford GU2 7XH Surrey England Univ Liverpool Dept Comp Sci Liverpool L69 3BX England UCL UCL Social Res Inst London WC1E 6BT England

Accurately assigning standardized diagnosis and procedure codes from clinical text is crucial for healthcare applications. However, this remains challenging due to the complexity of medical language. This paper proposes a novel model that incorporates extreme multi-label classification tasks to enhance International Classification of Diseases (icd) coding. The model utilizes deformable convolutional neural networks to fuse representations from hidden layer outputs of pre-trained language models and external medical knowledge embeddings fused using a multimodal approach to provide rich semantic encodings for each code. A probabilistic label tree is constructed based on the hierarchical structure existing in icd labels to incorporate ontological relationships between icd codes and enable structured output prediction. Experiments on medical code prediction on the MIMIC-III database demonstrate competitive performance, highlighting the benefits of this technique for robust clinical code assignment.

关键词： Natural language processing icd coding Extreme multi-label classification Few-shot learning Medical knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Automated icd coding for coronary heart diseases by a deep learning method

引用

HELIYON 2023年第3期9卷 e14037页

作者： Zhao, Shuai Diao, Xiaolin Xia, Yun Huo, Yanni Cui, Meng Wang, Yuxin Yuan, Jing Zhao, Wei Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Dept Informat Ctr Beijing 100037 Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Med Record Dept Beijing 100037 Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Dept Informat Ctr Natl Ctr Cardiovasc Dis Beijing 100037 Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Natl Ctr Cardiovasc Dis Beijing 100037 Peoples R China

Automated icd coding via machine learning that focuses on some specific diseases has been a hot topic. As one of the leading causes of death, coronary heart diseases (CHD) have seldom been specifically studied by related research, probably due to lack of data concretely targeting at the diseases. Based on Fuwai-CHD and MIMIC-III-CHD, which are a private dataset from Fuwai Hospital and the CHD-related subset of a public dataset named MIMIC-III respectively, this study aimed at automated CHD coding by a deep learning method, which mainly consists of three modules. The first is a BERT variant module responsible for encoding clinical text. In the module, we fine-tuned BERT variants with masked language model on clinical text, and proposed a truncation method to tackle the problem that BERT variants generally cannot handle sequences containing more than 512 tokens. The second is a word2vec module for encoding code titles and the third is a label -attention module for integrating the embeddings of clinical text and code titles. In short, we named the method BW_att. We compared BW_att against some widely studied baselines, and found that BW_att performed best in most of the coding missions. Specifically, BW_att reached a Macro-F1 of 96.2% and a Macro-AUC of 98.9% for the top-100 most frequent codes in Fuwai-CHD, which covered 89.2% of the total code occurrences. When predicting the top-50 most frequent codes in MIMIC-III-CHD, BW_att reached a Macro-F1 of 40.5% and a Macro-AUC of 66.1%. Moreover, BW_att was capable of locating informative tokens from clinical text for predicting the target codes. In summary, BW_att can not only suggest CHD codes accurately, but also possess robust interpretability, hence has great potential in facilitating CHD coding in practice.

关键词： icd coding Coronary heart diseases Deep learning BERT Interpretability

来源：评论

学校读者我要写书评

暂无评论

Application of Quality Control Circle in icd coding of Medical Records

引用

Chinese Medical Record English Edition 2013年第10期1卷 439-441页

Objective. To decrease the error rate of icd coding of medical records and improve the performance level of medical records staff and their management *** quality control circle activities are applied to the icd coding of medical records and all the activities are implemented according to the ten steps of the activities of the quality control circle. The coding error rates are compared between the data before and after the activity, and the improvement degree is calculated, the tangible results and the intangible results are *** the quality control circle activities are conducted, the number of the cases with coding errors is decreased obviously and the icd-coding error rate of the medical records is decreased from 24.57% before the activities to 8.13% after the activities, with an improvement rate of 66.90%. The staffs obviously improve themselves in the aspects of skill application in the quality control circle activities, team cohesiveness, learning initiative and sense of group ***. The management level and the working skill of the staff are improved by the quality control circle activities, and the working procedures are standardized and the error rate of the icd coding in the medical records is decreased, thus the coding quality of medical records is improved.

关键词： Quality control circle icd coding Reason of error coding

来源：评论

学校读者我要写书评

暂无评论

Comparison of icd coding between Mortality Statistics and Study-intern Retrospective Re-coding

引用

GESUNDHEITSWESEN 2009年第4期71卷 220-225页

作者： Klug, S. J. Bardehle, D. Ressing, M. Schmidtmann, I. Blettner, M. Univ Klin Mainz Inst Med Biometrie Epidemiol & Informat Mainz Germany Univ Bielefeld Fak Gesundheitswissensch Abt Epidemiol & Int Publ Hlth Bielefeld Germany

Objectives: The aim of this study was to assess agreement between study-intern nosologist death certificate coding and official mortality statistics icd codes. Methods: During the follow-up of a historical cohort study conducted in Germany, original death certificates were obtained for deceased cohort members and icd coded by a study-intern nosologist. Additionally, icd codes for these study subjects were obtained from a state statistical office responsible for mortality statistics. A weighted inter-observer agreement for these two sources was calculated. Results: In total, 406 icd codes were available from both sources. 219 (53.9%) of these icd codes completely agreed on the highest level possible (three- or four-digits). Agreement was found on the three-digit level with a difference at the fourth digit in 42 (10.3%) causes of death. Agreement within diagnosis groups or within chapters of disease was found in 21 (5.2%) and 49 (12.1%) causes of death, respectively. The weighted kappa for the overall inter-observer agreement was 0.67 [95% confidence interval (0): 0.63-0.71]. Within chapters of disease, agreement was higher for neoplasms (kappa=0.88;95% CI: 0.83-0.93) than for cardiovascular diseases (kappa=0.69;CI: 0.62-0.76). Conclusions: Overall level of agreement between the two coding sources was not very good. In Germany, the quality of coding has not improved substantially in the past two decades. The introduction of automatic coding systems, multicausal coding and a mortality register could improve the quality of icd coding in Germany.

关键词： cause of death death certificate icd coding mortality

来源：评论

学校读者我要写书评

暂无评论

Multi-features-Based Automatic Clinical coding for Chinese icd-9-CM-3 30th

Multi-features-Based Automatic Clinical Coding for Chinese I...

引用

30th International Conference on Artificial Neural Networks (ICANN)

作者： Gao, Yue Fu, Xiangling Liu, Xien Wu, Ji Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch Beijing Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China Beijing Univ Posts & Telecommun Key Lab Trustworthy Distributed Comp & Serv Minist Educ Beijing Peoples R China

ISBN: (纸本)9783030863838;9783030863821

icd-9-CM Volume 3 (icd-9-CM-3), as a subset of the icd-9-CM, is a standard system used to classify operations and medical procedures for billing purposes. With the gradual maturity of the DRG system, the precise coding of icd-9-CM-3 is increasingly important for both hospital revenue and patients' health. In this paper, a method based on BERT and NER capturing Multi-Features for automatic Chinese icd-9-CM-3 coding (BNMF) is proposed to support doctors to make decisions so that traditional manual coding in hospitals can be replaced. The method is designed focusing on short text information from electronic medical records (EMR) and make decisions by combining the semantic features of the clinical text, the structured features of Chinese icd-9-CM-3, and the axis knowledge of Chinese icd-9-CM-3 text. Meanwhile, fusion of spatial and temporal features is made to better capture semantic features. The experiments demonstrate that the efficiency of our framework is higher than those of state-of-the-art methods in the field of classification of the short medical corpus.

关键词： icd coding Decision support system Medical informatics Natural language processing

来源：评论

学校读者我要写书评

暂无评论

icd-10 Online coding Based on Electronic Medical Record System

引用

Chinese Medical Record English Edition 2013年第7期1卷 286-288页

With the development of medical information technology, especially the exploitation and application of the electronic medical record (EMR) system, the icd-10 online coding has become a development trend. Designing function modules of online coding as well as optimizing and reconstructing medical record management process according to practical situations together lead to the promotion of online quality control and coding, thereby helping to continuously improve the quality of the homepage of the medical record and the information sharing degree. Further, the timeliness of the medical record information and the integrity of EMR are ensured.

关键词： icd coding Electronic medical record Quality control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：